Spiking Neural Network (SNN) With Memristor Synapses Having Non-linear Weight Update.

Taeyoon Kim,Joon Young Kwak,Inho Kim,Jaewook Kim,Jong-Keuk Park,Jongkil Park,Suman Hu,Yeonjoo Jeong,Suyoun Lee

doi:10.3389/fncom.2021.646125

Taeyoon Kim, Joon Young Kwak + Show 7 more

Open Access

https://doi.org/10.3389/fncom.2021.646125

Copy DOI

Abstract

Among many artificial neural networks, the research on Spike Neural Network (SNN), which mimics the energy-efficient signal system in the brain, is drawing much attention. Memristor is a promising candidate as a synaptic component for hardware implementation of SNN, but several non-ideal device properties are making it challengeable. In this work, we conducted an SNN simulation by adding a device model with a non-linear weight update to test the impact on SNN performance. We found that SNN has a strong tolerance for the device non-linearity and the network can keep the accuracy high if a device meets one of the two conditions: 1. symmetric LTP and LTD curves and 2. positive non-linearity factors for both LTP and LTD. The reason was analyzed in terms of the balance between network parameters as well as the variability of weight. The results are considered to be a piece of useful prior information for the future implementation of emerging device-based neuromorphic hardware.

Highlights

The rapid growth of technological and industrial interests in artificial intelligence (AI) represented by machine learning (ML) was appearing in the various tasks from recognition of images (Liu et al, 2020) and sounds (Jung et al, 2020) to behavioral controls of autonomous cars and robots (Atzori et al, 2016; Gao et al, 2019)
A spiking neural network (SNN) is an artificial neural network constructed using the knowledge observed in biology, in which neurons communicate with each other using spikes via synapses connecting the neurons with adjustable weight values (Ghosh-Dastidar and Adeli, 2009)
We have conducted an SNN simulation with memristor synapse models having non-linear conductance change

Summary

INTRODUCTION

The rapid growth of technological and industrial interests in artificial intelligence (AI) represented by machine learning (ML) was appearing in the various tasks from recognition of images (Liu et al, 2020) and sounds (Jung et al, 2020) to behavioral controls of autonomous cars and robots (Atzori et al, 2016; Gao et al, 2019). Called resistive switching memory, is one of the emerging devices that can be used as an efficient synapse block when building a future neuromorphic system It has a tunable conductance directly representing a synaptic weight in biology and a spike signal received from the pre-neuron is transferred to the following post-neuron in the form of an electric current (or charge) proportional to the conductance of memristor (Jo et al, 2010). Systematic research on how and why the network degrades by the device non-ideality is strongly demanded future robust implementation of emerging device-based neuromorphic hardware. We analyzed that balances in network parameters such as LTP/LTD ratio and homeostasis are broken by the non-ideal device characteristics, causing degradation of the accuracy. The results can provide useful information for the future implementation of emerging device-based neuromorphic hardware

RESULTS AND DISCUSSIONS

CONCLUSION

DATA AVAILABILITY STATEMENT